minimaxiH3 Get access
QwenText-to-videoVendor content policy applies

Wan-2.6 Text-to-video

A speed-optimized text-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing.

$0.11per secondStarting price at the base resolution and quality tier.
$0.84Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A cinematic sci-fi trailer. Shot 1: Wide shot, a lonely explorer in a battered spacesuit walking across a desolate red Martian desert, a massive derelict spaceship in the distance. Shot 2: Close-up, the explorer stops an…”

What it does

Wan-2.6 Text-to-video, in practice.

Alibaba WAN 2.6 is an advanced text-to-video model provided by Alibaba Cloud's DashScope platform. This model generates high-quality 480p/720p/1080p videos from text prompts.

  • More affordable: Wan 2.6 is more streamlined and cost-effective - reducing
  • One-pass A/V sync: Wan 2.6 creates a fully synchronized video
  • Multilingual friendly: Wan 2.6 reliably processes like Chinese prompts
  • Longer duration & more video size options: Wan 2.6 delivers up to
  • Multi-shot storytelling: Generates cohesive multi-shot narratives,
  • Video reference generation: Uses a reference video's appearance and

Run Wan-2.6 Text-to-video

from $0.11/sec
duration
size
shot_type
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
audioAudio URL to guide generation (optional).
durationThe duration of the generated media in seconds.5 10 15
enable_prompt_expansionIf set to true, the prompt optimizer will be enabled.default True
negative_promptNegative prompt for the generation.
promptThe prompt for generating the output.
seedThe random seed to use for the generation. -1 means a random seed will be used.default -1
sizeThe size of the generated media in pixels (width*height).1280*720 720*1280 960*960 1088*832 832*1088 1920*1080 1080*1920 1440*1440 1632*1248 1248*1632
shot_typeGenerate video in multi camera angles, only works when set enable_prompt_expansion to true.multi single
generate_audioWhether to automatically add audio to the generated video.default True

Sample prompt

The prompt behind the sample.

A cinematic sci-fi trailer. Shot 1: Wide shot, a lonely explorer in a battered spacesuit walking across a desolate red Martian desert, a massive derelict spaceship in the distance. Shot 2: Close-up, the explorer stops and wipes dust off their helmet visor, eyes widening in shock. Shot 3: Over-the-shoulder shot, revealing a glowing, bioluminescent blue flower blooming rapidly in front of them. 8k resolution, highly detailed, consistent character.
seed: -1size: 1920*1080duration: 15shot_type: multienable_prompt_expansion: True

FAQ

Short answers.

How much does Wan-2.6 Text-to-video cost?

Pricing starts at $0.11 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $0.84. Usage is billed per request from your balance — no subscription.

Does Wan-2.6 Text-to-video run uncensored here?

No. Qwen applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Wan-2.6 Text-to-video for everything else it does well.

What does Wan-2.6 Text-to-video take as input?

It is a text-to-video model. A speed-optimized text-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Wan-2.6 Text-to-video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models